Assessment of Phytoecological Variability by Red-Edge Spectral Indices and Soil-Landscape Relationships

There is a relation of vegetation physiognomies with soil and geological conditions that can be represented spatially with the support of remote sensing data. The goal of this research was to map vegetation physiognomies in a mountainous area by using Sentinel-2 Multispectral Instrument (MSI) data and morphometrical covariates through data mining techniques. The research was based on red-edge (RE) bands, and indices, to classify phytophysiognomies at two taxonomic levels. The input data was pixel sampled based on field sample sites. Data mining procedures comprised covariate selection and supervised classification through the Random Forest model. Results showed the potential of bands 3, 5, and 6 to map phytophysiognomies for both seasons, as well as Green Chlorophyll (CLg) and SAVI indices. NDVI indices were important, particularly those calculated with bands 6, 7, 8, and 8A, which were placed at the RE position. The model performance showed reasonable success to Kappa index 0.72 and 0.56 for the first and fifth taxonomic level, respectively. The model presented confusion between Broadleaved dwarf-forest, Parkland Savanna, and Bushy grassland. Savanna formations occurred variably in the area while Bushy grasslands strictly occur in certain landscape positions. Broadleaved forests presented the best performance (first taxonomic level), and among its variation (fifth level) the model could precisely capture the pattern for those on deep soils from gneiss parent material. The approach was thus useful to capture intrinsic soil-plant relationships and its relation with remote sensing data, showing potential to map phytophysiognomies in two distinct taxonomic levels in poorly accessible areas.

Download Full-text

Application of the Parallel Spatial Association Rule in Remote Sensing Data Mining

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.500.598 ◽

2012 ◽

Vol 500 ◽

pp. 598-602

Author(s):

Jun Ma ◽

Dong Dong Zhang

Keyword(s):

Remote Sensing ◽

Data Mining ◽

Association Rule ◽

Spatial Association ◽

Remote Sensing Data ◽

Inner Product ◽

Data Mining Algorithm ◽

Sensing Data ◽

The Common ◽

Frequent Item Sets

Since the remote sensing data are multi-resources and massive, the common data mining algorithm cannot effectively discover the knowledge what people want to know. However, spatial association rule can solve the problem of inefficiency in remote sensing data mining. This paper gives an algorithm to compute the frequent item sets though a method like calculating vectors inner-product. And the algorithm will introduce pruning in the whole running. It reduces the time and resources consumption effectively

Download Full-text

Surge potential and drainage-basin characteristics in East Greenland

Annals of Glaciology ◽

10.3189/172756403781816220 ◽

2003 ◽

Vol 36 ◽

pp. 142-148 ◽

Cited By ~ 39

Author(s):

Hester Jiskoot ◽

Tavi Murray ◽

Adrian Luckman

Keyword(s):

Remote Sensing ◽

Drainage Basin ◽

Remote Sensing Data ◽

Environmental Data ◽

Glacier Inventory ◽

East Greenland ◽

Sensing Data ◽

Logistic Analysis ◽

Geological Conditions ◽

Multivariate Logistic Analysis

AbstractWe introduce a new glacier inventory of central East Greenland and use the collected data to test proposed theories on surging. The glacier inventory contains 259 glaciers, of which 10 have observed surges and a further 61 are inferred surge-type. The total glaciated area is 5.5×103 km2. The inventory was created from a combination of remote-sensing data and maps, and some 24 glacial and geological inventory parameters were collected for each glacier. A multivariate logistic analysis is used to test which combination of glacial and environmental data is conducive to surging behaviour in East Greenland. Three different models suggest that glaciers with a large complexity, low slope and oriented in a broad arc from northeast to south are most likely to be of surge type. Geological conditions, and hence substrate character, appeared not to be related to surge potential. On the basis of these results and the surge dynamics in this region, we suggest a hydrologically controlled surge mechanism operates in central East Greenland.

Download Full-text

Framework for network-level pavement condition assessment using remote sensing data mining

Journal of Applied Remote Sensing ◽

10.1117/1.jrs.14.024504 ◽

2020 ◽

Vol 14 (02) ◽

pp. 1

Author(s):

Stefanos S. Politis ◽

Zhanmin Zhang ◽

Sareh Kouchaki ◽

Carlos H. Caldas

Keyword(s):

Remote Sensing ◽

Data Mining ◽

Remote Sensing Data ◽

Condition Assessment ◽

Pavement Condition ◽

Sensing Data ◽

Pavement Condition Assessment

Download Full-text

Estimation of area burned by forest fires in Mediterranean countries: A remote sensing data mining perspective

Forest Ecology and Management ◽

10.1016/j.foreco.2011.07.010 ◽

2011 ◽

Vol 262 (8) ◽

pp. 1597-1607 ◽

Cited By ~ 18

Author(s):

Carmen Quintano ◽

Alfonso Fernández-Manso ◽

Alfred Stein ◽

Wietske Bijker

Keyword(s):

Remote Sensing ◽

Data Mining ◽

Forest Fires ◽

Remote Sensing Data ◽

Sensing Data ◽

Area Burned ◽

Mediterranean Countries

Download Full-text

Remote Sensing Prospecting Deposit Model Using Aster Data: A Case Study from Southern Part of Taxkorgan Tajik Autonomous County, China

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.733.124 ◽

2015 ◽

Vol 733 ◽

pp. 124-129

Author(s):

Hui Zhi Wu ◽

Qi Gang Jiang ◽

Chao Jun Bai

Keyword(s):

Remote Sensing ◽

Satellite Data ◽

Mineral Exploration ◽

Information Source ◽

Remote Sensing Data ◽

Screening Methods ◽

Data Sets ◽

Sensing Data ◽

Work Area ◽

Geological Conditions

This work uses multiple types of remote sensing data to develop a model-based mineral exploration method. Data used include Worldview-2 satellite data as the main information source supplemented by QuickBird satellite data to assist in geological interpretations and ASTER satellite data to extract remote sensing anomalies. We have enhanced the spectral and spatial resolution of the remote sensing data using ENVI software. Human-computer interaction methods have been used to confirm the geological conditions. We have interpreted 24 distinct lithologic units, including various types of metamorphic and sedimentary rocks. A total of 471 remote sensing anomalies were delineated, consisting of 173 hydroxyl anomalies and 298 iron-staining anomalies. Geological background screening methods were applied to identify 98 remote sensing anomalies, of which 29 were recommended for further study. Based on the interpretation of anomalies extracted from the ASTER and other geological remote sensing data sets, we have established a typical-deposit prospecting model. In the model, we delineated remote sensing prospecting targets by considering: remote sensing anomalies, geologic bodies and structures, geophysical anomalies and geochemical anomalies. Using this model, we divided the work area into two zones based on types of mineral generation. Seven prospecting targets (one A class, three B class and three C class) were identified. Trenching and block sorting methods were conducted for field verification, and resulted in the discovery of two copper and two iron occurrences with commercial potential.

Download Full-text